G-Networks to Predict the Outcome of Sensing of Toxicity

Abstract

G-Networks and their simplified version known as the Random Neural Network have often been used to classify data. In this paper, we present a use of the Random Neural Network to the early detection of potential of toxicity chemical compounds through the prediction of their bioactivity from the compounds’ physico-chemical structure, and propose that it be automated using machine learning (ML) techniques. Specifically the Random Neural Network is shown to be an effective analytical tool to this effect, and the approach is illustrated and compared with several ML techniques.

Surface-Related Features Responsible for Cytotoxic Behavior of MXenes Layered Materials Predicted with Machine Learning Approach

“…Thus, we assume that it might be one of the solutions for reducing the number of toxicological studies needed, and allows for minimizing failures in future biological applications. Machine learning studies concerning toxicity of drug, molecules have been carried out previously, by using deep learning and XGBoost [15] approaches, and using Atomic Fingerprints [16][17][18][19][20][21]. However, to the best of our knowledge, there is a lack of toxicological research based on ML methods concerning layered materials, in particular, 2D structures.…”

Recent advances in the modification of electrodes for trace metal analysis: a review

“…Bismuth film electrodes (BiFEs) are among the most employed electrodes in the determination of trace heavy metals. 25,40,50,83,181,197,233,235,[245][246][247][248][249][250][251][252][253][254][255][256][257][258][259][260] In addition to its low toxicity and the ability to form alloys with other metals, bismuth has a wide potential range, which allows BiFEs to have comparable analytical performance to the mercury electrodes in trace heavy metal analysis. 7,243,244 The film can be electrochemically deposited directly on the electrode surface from the solution containing both the modifier and the analytes (in situ preparation) or through film deposition before the electrode is introduced in the sample solution (ex situ preparation).…”

“…In addition to the above-mentioned main groups of materials and/or compounds, in the last five years, the research community has also reported on the inclusion of calixarene-based compounds, 117,118,281,[305][306][307][308][309] ionic liquids (ILs), 55,155,168,258 and Schiff bases 156,310,311 as electrode modifiers for trace heavy metal analysis. Table S5 in the ESI † summarizes the main findings of the research studies published in the last five years reporting on the use of other organic compounds as modifiers for various types of electrodes employed in the determination of trace heavy metals.…”

“…Calix [4]arene-functionalized compounds were mostly used to modify GCEs (in addition to the SPCE and Au electrode) employed in the individual or simultaneous determination of Hg 2+ , Pb 2+ , Cd 2+ , Zn 2+ , and Cu 2+ in different real water samples (including wastewater, river, drinking, and deionized water) 117,118,[305][306][307]309 and commercial oysters, clams, and mussel samples. 308 Imidazolium- 155,168 and pyridinium-based 55,258 ILs are also among the organic compounds used to modify the electrodes. These ILs were always applied in combination with other materials and/or compounds (i.e., nanofibers, SWCNTs, Bi and Fe 3 O 4 -NPs, and L-cysteine).…”

“…The authors have attributed the increased sensitivity of the modified LEGE to the combination of the good conductivity of the IL and the complexing ability of poly-L-cysteine. The modified electrodes have been successfully employed in the individual or simultaneous determination of Pb 2+ and Cd 2+ in real water 55,168 and soil extract 155,258 samples. The ability of the Schiff bases to form complexes with metal ions through the lone pair electrons of O and N atoms in their structure makes this type of compound of interest potent in the modification of electrodes for trace metal analysis.…”